Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Super Bowls

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “Super Bowl” (often with its Roman‐numeral designation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    fp
    -0.07
    ?url
    -0.07
     Yar
    -0.06
     svém
    -0.06
     Dios
    -0.06
    尋
    -0.06
     لی
    -0.06
     面
    -0.06
    _ADDRESS
    -0.06
    Modify
    -0.06
    POSITIVE LOGITS
     Finn
    0.07
     confirming
    0.06
     support
    0.06
     reserv
    0.06
     شکل
    0.06
     concerned
    0.06
     tip
    0.06
     conflicts
    0.06
     prosecuted
    0.06
     Dangerous
    0.06
    Act Density 0.005%

    No Known Activations